Chord Predictive Intelligence Overview
Chord’s predictive data science capabilities help brands turn raw customer data into actionable intelligence. With Personas, Churn Predictions, and Purchase-Likelihood modeling available across the Chord platform—and accessible through both Copilot (AI chat) and analytics—teams can quickly activate smarter marketing and retention strategies.
1. What Chord Predictive Models Do
Chord applies machine-learning models to your customer and commerce data to surface insights such as:
- Customer Personas & Churn Predictions — Understand who your customers are (e.g., Deal-Seeker, Wellness Enthusiast, Loyalist) and which customers are at risk of dropping off. Personas help you tailor messaging and product experiences, while churn predictions help you intervene proactively.
- Likelihood to purchase or repurchase — Identify customers most likely to buy next.
- Customer lifetime revenue prediction (CLR) — Determine who will be most valuable long term.
- Behavioral and commercial patterns — Insights based on recency, frequency, spend, and engagement trends.
2. Why It Matters
Predictive intelligence helps teams:
- Spend smarter on acquisition
- Increase retention and customer lifetime value
- Personalize communication at scale
- Identify the right customers at the right moment
- Make decisions proactively rather than reactively
Chord’s models turn your customer data into a real competitive advantage—helping marketing, product, and analytics teams drive measurable growth.
3. How to Use These Insights in Chord
Model Name | Predict Level | Output Metric Name | Description | Notes | Input Metric(s) | Data Source(s) | Example Use Cases | Explore(s) |
|---|---|---|---|---|---|---|---|---|
Customer Lifetime Revenue (CLR) | User | Predicted Lifetime Revenue | Forecasted customer lifetime revenue | Based on historical patterns + user-specific behavior | Orders data, predicted customer ML features, sessions data | Orders, sessions, ML features | Retention targeting, VIP perks | Users |
RFM | User | Recency | Recency, frequency, and monetary scoring | Days since last order. Higher = more recent | Orders data | Orders | Segmentation, churn risk | Users |
RFM | User | Frequency | Recency, frequency, and monetary scoring | Number of orders in time window. Higher = more orders | Orders data | Orders | Segmentation, churn risk | Users |
RFM | User | Monetary | Recency, frequency, and monetary scoring | Total spend in time window. Higher = more spend | Orders data | Orders | Segmentation, churn risk | Users |
RFM | User | RFM Bucket | Recency, frequency, and monetary scoring | Combined RFM grouping | Orders data | Orders | Segmentation, churn risk | Users |
Predicted Repurchase | User | Repurchase Probability | Probability that the user will repurchase | Likelihood of buying again | Orders data, predicted customer ML features, sessions data | Orders, sessions, ML features | Win-back campaigns | |
Product Recommendations | User | Recommendations 1-5 | Top 5 recommended items for user | Top 5 predicted next purchases | Orders data, predicted customer ML features, sessions data | Orders, catalog, ML features | Cross-sell, personalization | Users |
Segmentation Clustering | User | Marketing Segment ID | Unstructured hierarchical cluster assignments | Used for targeting/lookalike audiences/personalization | Orders data, predicted customer ML features, sessions data | Orders, sessions, ML features | Audience targeting | |
Revenue Forecast | Company | Forecasted Revenue | Forecasted top-level revenue | Time series prediction | Time series order data | Orders | Budgeting, forecasting | Predicted Forecasts |
New Customer Forecast | Company | Forecasted New Customer Count | Forecasted count of new customers | Time series prediction | Time series order data | Orders | Acquisition planning | Predicted Forecasts |
Returning Customer Forecast | Company | Forecasted Returning Customer Count | Forecasted count of returning customers | Time series prediction | Time series order data | Orders | Retention planning | Predicted Forecasts |
Probability to Convert | Sessions | Conversion Probability | Probability a session will convert to a paid customer | Likelihood session converts | Sessions and orders data | Sessions, orders | On-site personalization | Sessions, Marketing Attribution - Order Attribution, Marketing Attribution - User Attribution |
Predictive Marketing Attribution | Orders | Attribution % by Channel | Fractional revenue attribution by channel | Model-weighted attribution | Marketing spend, conversions | Spend, conversions | Channel optimization | Marketing Attribution - Order Attribution, Marketing Attribution - User Attribution |
Customer Personas | Users | User Persona Name | Customer segment grouping based on purchase behavior | Personas group customers with similar purchasing patterns and predicted lifetime value. | Customer email | Customer email | Personalization, audience targeting | |
Likelihood to Churn (Percentile) | Users | User Churn Propensity Percentile | Identify customers at risk of churning | Higher percentiles = higher likelihood of churning | Customer email | Customer email | Retention planning, churn risk | |
Likelihood to Churn (Probability) | Users | User Churn Propensity Percentile | Identify customers at risk of churning | Higher values = higher probability of churning | Customer email | Customer email | Retention planning, churn risk | |